An Automated Design Flow for Adaptive Neural Network Hardware Accelerators
-
Published:2023-04-26
Issue:9
Volume:95
Page:1091-1113
-
ISSN:1939-8018
-
Container-title:Journal of Signal Processing Systems
-
language:en
-
Short-container-title:J Sign Process Syst
Author:
Ratto Francesco, Máinez Ángela Porras, Sau CarloORCID, Meloni Paolo, Deriu Gianfranco, Delucchi Stefano, Massa Massimo, Raffo Luigi, Palumbo Francesca
Abstract
AbstractImage and video processing are one of the main driving application fields for the latest technology advancement of computing platforms, especially considering the adoption of neural networks for classification purposes. With the advent of Cyber Physical Systems, the design of devices for efficiently executing such applications became more challenging, due to the increase of the requirements to be considered, of the functionalities to be supported, as well as to the demand for adaptivity and connectivity. Heterogeneous computing and design automation are then turning into essential. The former guarantees a variegated set of features under strict constraints (e.g., by adopting hardware acceleration), and the latter limits development time and cost (e.g., by exploiting model-based design). In this context, the literature is still lacking adequate tooling for the design and management of neural network hardware accelerators, which can be adaptable and customizable at runtime according to the user needs. In this work, a novel almost automated toolchain based on the Open Neural Network eXchange format is presented, allowing the user to shape adaptivity right on the network model and to deploy it on a runtime reconfigurable accelerator. As a proof of concept, a Convolutional Neural Network for human/animal classification is adopted to derive a Field Programmable Gate Array accelerator capable of trading execution time for power by changing the resources involved in the computation. The resulting accelerator, when necessary, can consume 30% less power on each layer, taking about overall 8% more time to classify an image.
Funder
Electronic Components and Systems for European Leadership H2020 LEIT Information and Communication Technologies Università degli Studi di Sassari
Publisher
Springer Science and Business Media LLC
Subject
Hardware and Architecture,Modeling and Simulation,Information Systems,Signal Processing,Theoretical Computer Science,Control and Systems Engineering
Reference50 articles.
1. An FPGA “Companion” in Smartphone Design - A Lattice Semiconductor White Paper. Document ID 47335 (2012-05). 2. Al-Ars, Z., et al. (2019). The fitoptivis ECSEL project: highly efficient distributed embedded image/video processing in cyber-physical systems. In Conference on Computing Frontiers (pp. 333–338). 3. Pomante, L., Palumbo, F., Rinaldi, C., Valente, G., Sau, C., Fanni, T., van der Linden, F., Basten, T., Geilen, M., Peeren, G., Kadlec, J., Jääskeläinen, P., de Alejandro, M. M., Saarinen, J., Säntti, T., Zedda, M. K., Sanchez, V., Goswami, D., Al-Ars, Z., & de Beer, A. (2020). Design and management of image processing pipelines within CPS: 2 years of experience from the fitoptivis ECSEL project. In 23rd Euromicro Conference on Digital System Design, DSD 2020, Kranj, Slovenia, August 26-28, 2020 (pp. 378–385). IEEE. Retrieved April 2023, from https://www.latticesemi.com/-/media/LatticeSemi/Documents/WhitePapers/AG/AnFPGACompanioninSmartphoneDesign.ashx?document_id=47335 4. Beaumin, C., Sentieys, O., Casseau, E., & Carer, A. (2010). A coarse-grain reconfigurable hardware architecture for RVC-CAL-based design. In 2010 Conference on Design and Architectures for Signal and Image Processing (DASIP) (pp. 152–159). https://doi.org/10.1109/DASIP.2010.5706259 5. Fanni, T., Rodríguez, A., Sau, C., Suriano, L., Palumbo, F., Raffo, L., & de la Torre, E. (2018). Multi-grain reconfiguration for advanced adaptivity in cyber-physical systems. In 2018 International Conference on ReConFigurable Computing and FPGAs (ReConFig) (pp. 1–8). https://doi.org/10.1109/RECONFIG.2018.8641705
|
|